diff options
Diffstat (limited to 'src/modules/filters/utf8nfkd.cpp')
| -rw-r--r-- | src/modules/filters/utf8nfkd.cpp | 23 |
1 files changed, 15 insertions, 8 deletions
diff --git a/src/modules/filters/utf8nfkd.cpp b/src/modules/filters/utf8nfkd.cpp index 450cbbf..6da24f8 100644 --- a/src/modules/filters/utf8nfkd.cpp +++ b/src/modules/filters/utf8nfkd.cpp @@ -1,13 +1,12 @@ /****************************************************************************** * -* utf8nfkd - SWFilter decendant to perform NFKD (compatability decomposition +* utf8nfkd - SWFilter descendant to perform NFKD (compatability decomposition * normalization) on UTF-8 text */ #ifdef _ICU_ #include <stdlib.h> -#include <string.h> #ifdef __GNUC__ #include <unixstr.h> @@ -15,6 +14,8 @@ #include <utf8nfkd.h> +SWORD_NAMESPACE_START + UTF8NFKD::UTF8NFKD() { conv = ucnv_open("UTF-8", &err); } @@ -23,24 +24,30 @@ UTF8NFKD::~UTF8NFKD() { ucnv_close(conv); } -char UTF8NFKD::ProcessText(char *text, int maxlen, const SWKey *key, const SWModule *module) +char UTF8NFKD::processText(SWBuf &text, const SWKey *key, const SWModule *module) { - int32_t len = strlen(text) * 2; + if ((unsigned long)key < 2) // hack, we're en(1)/de(0)ciphering + return -1; + + int32_t len = text.length() * 2; source = new UChar[len + 1]; //each char could become a surrogate pair // Convert UTF-8 string to UTF-16 (UChars) - len = ucnv_toUChars(conv, source, len, text, -1, &err); + len = ucnv_toUChars(conv, source, len, text.c_str(), -1, &err); target = new UChar[len + 1]; //compatability decomposition unorm_normalize(source, len, UNORM_NFKD, 0, target, len, &err); - ucnv_fromUChars(conv, text, maxlen, target, -1, &err); + text.setSize(text.size()*2); + len = ucnv_fromUChars(conv, text.getRawData(), text.size(), target, -1, &err); + text.setSize(len); - delete [] source; - delete [] target; + delete [] source; + delete [] target; return 0; } +SWORD_NAMESPACE_END #endif |